© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15385
    Prev
    Next
    INDEX
    Explanations

    references to the first occurrence of a specific event or identifier

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ending
    -1.13
    ending
    -1.09
    ended
    -0.99
     myſelf
    -0.96
     Ending
    -0.96
     itſelf
    -0.92
    RenderAtEndOf
    -0.91
     Ended
    -0.86
     Theſe
    -0.86
    ENDED
    -0.84
    POSITIVE LOGITS
     ends
    1.67
     Ends
    1.30
     ENDS
    1.03
    Ends
    0.87
    PathVariable
    0.59
     extremos
    0.54
     tu
    0.53
    canActivate
    0.52
    端に
    0.50
     edges
    0.48
    Activations Density 0.003%

    No Known Activations